What are the hardware requirements for K2 Horizon 7B?

K2 Horizon 7B requires approximately 18.5 GB of VRAM and supports a context window of 512K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed K2 Horizon 7B and how large is it?

K2 Horizon 7B is developed by IFM, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate K2 Horizon 7B?

K2 Horizon 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

K2 Horizon 7B by IFM — VRAM 18.5GB, 512K context

Name: K2 Horizon 7B
Author: IFM

K2 Horizon 7B is an open-source language model by IFM. Features: 7b LLM, VRAM: 18.5GB, Context: 512K, License: apache-2.0, LLM Explorer Score: 0.32.

7b Conversational Custom code Dataset:ifm/k2-horizon-midtrai... Dataset:ifm/k2-horizon-pretrai... Dense En Ifm K2-horizon K2 horizon Open-weights Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/IFM/K2-Horizon-7B

K2 Horizon 7B Parameters and Internals

LLM Name	K2 Horizon 7B
Repository 🤗	https://huggingface.co/IFM/K2-Horizon-7B
Model Name	K2-Horizon-7B
Model Size	7b
Required VRAM	18.5 GB
Updated	2026-09-04
Maintainer	IFM
Model Type	k2_horizon
Model Files	0.4 GB: 1-of-36 0.4 GB: 2-of-36 0.4 GB: 3-of-36 0.4 GB: 4-of-36 0.4 GB: 5-of-36 0.4 GB: 6-of-36 0.4 GB: 7-of-36 0.4 GB: 8-of-36 0.4 GB: 9-of-36 0.4 GB: 10-of-36 0.4 GB: 11-of-36 0.4 GB: 12-of-36 0.4 GB: 13-of-36 0.4 GB: 14-of-36 0.4 GB: 15-of-36 0.4 GB: 16-of-36 0.4 GB: 17-of-36 0.4 GB: 18-of-36 0.4 GB: 19-of-36 0.4 GB: 20-of-36 0.4 GB: 21-of-36 0.4 GB: 22-of-36 0.4 GB: 23-of-36 0.4 GB: 24-of-36 0.4 GB: 25-of-36 0.4 GB: 26-of-36 0.4 GB: 27-of-36 0.4 GB: 28-of-36 0.4 GB: 29-of-36 0.4 GB: 30-of-36 0.4 GB: 31-of-36 0.4 GB: 32-of-36 0.4 GB: 33-of-36 0.4 GB: 34-of-36 0.4 GB: 35-of-36 4.5 GB: 36-of-36
Supported Languages	en
Model Architecture	K2HorizonForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	5.13.0
Tokenizer Class	TokenizersBackend
Vocabulary Size	250624

Rank the K2 Horizon 7B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the K2 Horizon 7B

Model	Likes	Downloads	VRAM
K2 Horizon 7B 4bit	1	295	7 GB
K2 Horizon 7B MLX 4bit	3	375	5 GB

Best Alternatives to K2 Horizon 7B

Best Alternatives	Context / RAM	Downloads	Likes
Jais 3 7B	512K / 17.9 GB	875	5
K2 Horizon 7B Heretic	512K / 18 GB	193	0
K2 Horizon 7B Uno Merged	512K / 18 GB	475	2
K2 Horizon 7B Uno OQ6e	512K / 7.5 GB	348	1
K2 Horizon 7B OQ6e	512K / 7.5 GB	352	2
BetterWright K2 Horizon 7B Uno	512K / 18 GB	168	1
K2 Horizon 7B FP8	512K / 11.1 GB	185	6
K2 Horizon 7B 4bit	512K / 7.2 GB	295	1
K2 Horizon 7B MLX 4bit	512K / 5.1 GB	375	3